Araştırma Makalesi

Predicting Building Heating and Cooling Loads Using Hyperparameter Optimization and SHAP Based Explainable Machine Learning

Sayı: Advanced Online Publication Erken Görünüm Tarihi: 14 Kasım 2026
PDF İndir
EN TR

Predicting Building Heating and Cooling Loads Using Hyperparameter Optimization and SHAP Based Explainable Machine Learning

Öz

This study aimed to predict building heating and cooling loads from geometric and glazing characteristics and to explain the resulting model predictions. The UCI Energy Efficiency dataset was used, comprising 768 building configurations, eight input features, and two continuous targets. First, 14 regression algorithms were compared using test metrics and tenfold cross-validation. The hyperparameters of six algorithms were then optimized using RandomizedSearchCV with fivefold cross-validation. Performance was assessed using RMSE, MAE, MAPE, and R². Histogram Gradient Boosting achieved the lowest test RMSE for both targets in the initial comparison, whereas Gradient Boosting performed best after optimization. For heating load, the optimized model achieved an RMSE of 0.34048, an MAE of 0.24123, a MAPE of 1.14%, and an R² of 0.99889. The corresponding cooling-load values were 0.81253, 0.51096, 1.84%, and 0.99287. SHAP analysis identified relative compactness, surface area, and overall height as the leading contributors to heating predictions, while roof area, surface area, and relative compactness were most prominent for cooling. The results indicate that optimized boosting models can predict thermal loads with low error within the simulated configurations examined. Strong dependence among geometric features requires their SHAP contributions to be interpreted jointly. By combining predictive performance and model explanations within a common evaluation framework, the study provides an application of explainable machine learning to building energy assessment.

Anahtar Kelimeler

Kaynakça

  1. [1] Gassar, A. A. A., Koo, C., Kim, T. W., & Cha, S. H. (2021). Performance optimization studies on heating, cooling and lighting energy systems of buildings during the design stage: A review. Sustainability, 13(17), 9815.
  2. [2] Korolija, I., Marjanovic-Halburd, L., Zhang, Y., & Hanby, V. I. (2013). UK office buildings archetypal model as methodological approach in development of regression models for predicting building energy consumption from heating and cooling demands. Energy and Buildings, 60, 152-162.
  3. [3] Romaios, A., Paravantis, J. A., Giannadakis, A., Malefaki, S., Souliotis, M., Antzoulatou, A., ... & Mihalakakou, G. (2026). Simulation‐Based and Machine Learning Methodologies for Energy Optimization in Buildings. Wiley Interdisciplinary Reviews: Energy and Environment, 15(1), e70021.
  4. [4] Bertoni, A., Hallstedt, S. I., Dasari, S. K., & Andersson, P. (2020). Integration of value and sustainability assessment in design space exploration by machine learning: an aerospace application. Design Science, 6, e2.
  5. [5] Menezes, A. C., Cripps, A., Bouchlaghem, D., & Buswell, R. (2012). Predicted vs. actual energy performance of non-domestic buildings: Using post-occupancy evaluation data to reduce the performance gap. Applied energy, 97, 355-364.
  6. [6] Fisher, A., Rudin, C., & Dominici, F. (2019). All models are wrong, but many are useful: Learning a variable's importance by studying an entire class of prediction models simultaneously. Journal of machine learning research, 20(177), 1-81.
  7. [7] Tsanas, A., & Xifara, A. (2012). Energy efficiency [Data set]. UCI Machine Learning Repository. https://doi.org/10.24432/C51307
  8. [8] Dal, S., & Sezgın, N. (2024, December). Optimal parameter extraction of triple-diode photovoltaic model using frilled lizard optimization. In 2024 Global Energy Conference (GEC) (pp. 1-5). IEEE.

Ayrıntılar

Birincil Dil

İngilizce

Konular

Elektrik Mühendisliği (Diğer)

Bölüm

Araştırma Makalesi

Erken Görünüm Tarihi

14 Kasım 2026

Yayımlanma Tarihi

-

Gönderilme Tarihi

30 Ekim 2026

Kabul Tarihi

10 Kasım 2026

Yayımlandığı Sayı

Yıl 2025 Sayı: Advanced Online Publication

Kaynak Göster

APA
Dal, S. (2026). Predicting Building Heating and Cooling Loads Using Hyperparameter Optimization and SHAP Based Explainable Machine Learning. European Journal of Technique (EJT), Advanced Online Publication. https://doi.org/10.36222/ejt.2074512
AMA
1.Dal S. Predicting Building Heating and Cooling Loads Using Hyperparameter Optimization and SHAP Based Explainable Machine Learning. EJT. 2026;(Advanced Online Publication). doi:10.36222/ejt.2074512
Chicago
Dal, Süleyman. 2026. “Predicting Building Heating and Cooling Loads Using Hyperparameter Optimization and SHAP Based Explainable Machine Learning”. European Journal of Technique (EJT), sy Advanced Online Publication. https://doi.org/10.36222/ejt.2074512.
EndNote
Dal S (14 Kasım 2026) Predicting Building Heating and Cooling Loads Using Hyperparameter Optimization and SHAP Based Explainable Machine Learning. European Journal of Technique (EJT) Advanced Online Publication
IEEE
[1]S. Dal, “Predicting Building Heating and Cooling Loads Using Hyperparameter Optimization and SHAP Based Explainable Machine Learning”, EJT, sy Advanced Online Publication, Kas. 2026, doi: 10.36222/ejt.2074512.
ISNAD
Dal, Süleyman. “Predicting Building Heating and Cooling Loads Using Hyperparameter Optimization and SHAP Based Explainable Machine Learning”. European Journal of Technique (EJT). Advanced Online Publication (14 Kasım 2026). https://doi.org/10.36222/ejt.2074512.
JAMA
1.Dal S. Predicting Building Heating and Cooling Loads Using Hyperparameter Optimization and SHAP Based Explainable Machine Learning. EJT. 2026. doi:10.36222/ejt.2074512.
MLA
Dal, Süleyman. “Predicting Building Heating and Cooling Loads Using Hyperparameter Optimization and SHAP Based Explainable Machine Learning”. European Journal of Technique (EJT), sy Advanced Online Publication, Kasım 2026, doi:10.36222/ejt.2074512.
Vancouver
1.Süleyman Dal. Predicting Building Heating and Cooling Loads Using Hyperparameter Optimization and SHAP Based Explainable Machine Learning. EJT. 14 Kasım 2026;(Advanced Online Publication). doi:10.36222/ejt.2074512